@inproceedings{yamaguchi-etal-2022-hitachi,
title = "Hitachi at {S}em{E}val-2022 Task 2: On the Effectiveness of Span-based Classification Approaches for Multilingual Idiomaticity Detection",
author = "Yamaguchi, Atsuki and
Morio, Gaku and
Ozaki, Hiroaki and
Sogawa, Yasuhiro",
editor = "Emerson, Guy and
Schluter, Natalie and
Stanovsky, Gabriel and
Kumar, Ritesh and
Palmer, Alexis and
Schneider, Nathan and
Singh, Siddharth and
Ratan, Shyam",
booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.semeval-1.15",
doi = "10.18653/v1/2022.semeval-1.15",
pages = "135--144",
abstract = "In this paper, we describe our system for SemEval-2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embedding. The task aims at detecting idiomaticity in an input sequence (Subtask A) and modeling representation of sentences that contain potential idiomatic multiword expressions (MWEs) (Subtask B) in three languages. We focus on the zero-shot setting of Subtask A and propose two span-based idiomaticity classification methods: MWE span-based classification and idiomatic MWE span prediction-based classification. We use several cross-lingual pre-trained language models (InfoXLM, XLM-R, and others) as our backbone network. Our best-performing system, fine-tuned with the span-based idiomaticity classification, ranked fifth in the zero-shot setting of Subtask A and exhibited a macro F1 score of 0.7466.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yamaguchi-etal-2022-hitachi">
<titleInfo>
<title>Hitachi at SemEval-2022 Task 2: On the Effectiveness of Span-based Classification Approaches for Multilingual Idiomaticity Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atsuki</namePart>
<namePart type="family">Yamaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaku</namePart>
<namePart type="family">Morio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroaki</namePart>
<namePart type="family">Ozaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasuhiro</namePart>
<namePart type="family">Sogawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shyam</namePart>
<namePart type="family">Ratan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe our system for SemEval-2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embedding. The task aims at detecting idiomaticity in an input sequence (Subtask A) and modeling representation of sentences that contain potential idiomatic multiword expressions (MWEs) (Subtask B) in three languages. We focus on the zero-shot setting of Subtask A and propose two span-based idiomaticity classification methods: MWE span-based classification and idiomatic MWE span prediction-based classification. We use several cross-lingual pre-trained language models (InfoXLM, XLM-R, and others) as our backbone network. Our best-performing system, fine-tuned with the span-based idiomaticity classification, ranked fifth in the zero-shot setting of Subtask A and exhibited a macro F1 score of 0.7466.</abstract>
<identifier type="citekey">yamaguchi-etal-2022-hitachi</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.15</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.15</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>135</start>
<end>144</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hitachi at SemEval-2022 Task 2: On the Effectiveness of Span-based Classification Approaches for Multilingual Idiomaticity Detection
%A Yamaguchi, Atsuki
%A Morio, Gaku
%A Ozaki, Hiroaki
%A Sogawa, Yasuhiro
%Y Emerson, Guy
%Y Schluter, Natalie
%Y Stanovsky, Gabriel
%Y Kumar, Ritesh
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Singh, Siddharth
%Y Ratan, Shyam
%S Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F yamaguchi-etal-2022-hitachi
%X In this paper, we describe our system for SemEval-2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embedding. The task aims at detecting idiomaticity in an input sequence (Subtask A) and modeling representation of sentences that contain potential idiomatic multiword expressions (MWEs) (Subtask B) in three languages. We focus on the zero-shot setting of Subtask A and propose two span-based idiomaticity classification methods: MWE span-based classification and idiomatic MWE span prediction-based classification. We use several cross-lingual pre-trained language models (InfoXLM, XLM-R, and others) as our backbone network. Our best-performing system, fine-tuned with the span-based idiomaticity classification, ranked fifth in the zero-shot setting of Subtask A and exhibited a macro F1 score of 0.7466.
%R 10.18653/v1/2022.semeval-1.15
%U https://aclanthology.org/2022.semeval-1.15
%U https://doi.org/10.18653/v1/2022.semeval-1.15
%P 135-144
Markdown (Informal)
[Hitachi at SemEval-2022 Task 2: On the Effectiveness of Span-based Classification Approaches for Multilingual Idiomaticity Detection](https://aclanthology.org/2022.semeval-1.15) (Yamaguchi et al., SemEval 2022)
ACL